Multi-Phase Plan
by Danejw
Convert product specs into a vertical-slice implementation roadmap with ready-to-use prompts for AI coding agents.
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
Based on my business-model.md and design docs, generate a vertical-slice implementation plan with prompts for an MVP. Ensure we avoid mock data and include a tasklist-roadmap.md.
Your agent does
multiphase-plan/ ├── tasklist-roadmap.md ├── phase-test-plan.md ├── phase-prompts/ │ ├── phase-01-auth-persistence.md │ └── phase-02-core-crud-flow.md └── resources/ └── implementation-rules.md
Phase 1 Goal: User can sign up and create a record that persists in the DB. No fake buttons.
What you get
About this skill
What it does
This skill transforms finalized product requirements and design documents into a structured, executable multiphase implementation plan. It moves beyond generic task lists by generating a downloadable build package designed specifically for AI coding agents like Cursor, Windsurf, or Bolt.new.
How it works
By analyzing your business model, design docs, and UX flows, the skill architects a series of "vertical slices." Instead of building horizontal layers (like "Database" then "API"), it creates phases where each step results in a fully functional, testable feature—such as "User can save a real project and see it in the dashboard."
Why use this skill
- Eliminates "AI Hallucinations": Enforces a strict "No Mock Data" rule, ensuring agents build real data boundaries and error handling rather than placeholder UIs.
- Bipasses Prompt Engineering: Generates ready-to-use markdown prompts for every phase, including context, scope, and completion criteria.
- Automated Testing: Integrates test-driven development by defining exactly what behaviors and states must be validated before a phase is marked complete.
- Progressive Disclosure: Includes a master tasklist roadmap that tracks progress without overwhelming the LLM's context window.
What you get
A comprehensive multiphase-plan/ directory containing a tasklist roadmap, a phase-specific test plan, implementation rules, and a series of detailed markdown prompts for sequential execution.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 2 months ago
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.